@inproceedings{wang-etal-2025-rico,
    title = "{RICO}: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction",
    author = "Wang, Yuchi  and
      Cai, Yishuo  and
      Ren, Shuhuai  and
      Yang, Sihan  and
      Yao, Linli  and
      Liu, Yuanxin  and
      Zhang, Yuanxing  and
      Wan, Pengfei  and
      Sun, Xu",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1105/",
    pages = "21796--21815",
    ISBN = "979-8-89176-332-6",
    abstract = "Image recaptioning is widely used to generate training datasets with enhanced quality for various multimodal tasks. Existing recaptioning methods typically rely on powerful multimodal large language models (MLLMs) to enhance textual descriptions, but often suffer from inaccuracies due to hallucinations and incompleteness caused by missing fine-grained details. To address these limitations, we propose RICO, a novel framework that refines captions through visual reconstruction. Specifically, we leverage a text-to-image model to reconstruct a caption into a reference image, and prompt an MLLM to identify discrepancies between the original and reconstructed images to refine the caption. This process is performed iteratively, further progressively promoting the generation of more faithful and comprehensive descriptions. To mitigate the additional computational cost induced by the iterative process, we introduce RICO-Flash, which learns to generate captions like RICO using DPO. Extensive experiments demonstrate that our approach significantly improves caption accuracy and completeness, outperforms most baselines by approximately 10{\%} on both CapsBench and CompreCap."
}